-
公开(公告)号：US20230087132A1
公开(公告)日：2023-03-23
申请号：US17478946
申请日：2021-09-19
Applicant: Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
Inventor： Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
IPC: G06F16/242 , G06F16/2457 , G06F16/248 , G06F16/22
Abstract: A method of creating action-trigger phrase sets includes receiving a document from a corpus of documents; processing text from the document; and creating an action-trigger phrase set from the text.
-
公开(公告)号：US20220300406A1
公开(公告)日：2022-09-22
申请号：US17202463
申请日：2021-03-16
Applicant: Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Inventor： Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Abstract: A method for alerting a community to potential problematic commits includes receiving a commit submitted by an author in a project; testing the commit using a pre-trained learning model; and determining if the commit is problematic, and if the commit is problematic, sending a report in the project outlining the level of risk of implementing the commit and a reason for the level or risk. Users of the project will be alerted to potential risk of particular commits.
-
公开(公告)号：US20220300261A1
公开(公告)日：2022-09-22
申请号：US17202452
申请日：2021-03-16
Applicant: Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Inventor： Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
IPC: G06F8/41 , G06N20/00 , G06F16/178
Abstract: A method of determining if a commit is problematic includes determining a complexity of the commit; determining an author of the commit; determining an experience of the author; determining a component affected by the commit; and assigning a risk value to the commit based on the complexity, the author, the experience of the author and the component affected.
-
公开(公告)号：US20220300405A1
公开(公告)日：2022-09-22
申请号：US17202460
申请日：2021-03-16
Applicant: Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Inventor： Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Abstract: A method for testing commits from a third-party product into a dependent product includes receiving a first commit from a third-party product; waiting for additional commits from the third-party product; receiving a second commit from the third-party product; testing the first and second commit using a pre-trained learning model; determining if the first commit is problematic, and if the first commit is problematic, sending the first commit for review before implementation; and determining if the second commit is problematic, and if the second commit is problematic, sending the second commit for review before implementation. Accumulating the first and second commits for testing at once reduces system resources.
-
Patent Agency Ranking
公开(公告)号：US20220121694A1
公开(公告)日：2022-04-21
申请号：US17478945
申请日：2021-09-19
Applicant: Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
Inventor： Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
IPC: G06F16/332 , G06F40/30 , G06F40/205
Abstract: An approach to information retrieval is contemplated for facilitating semantic search and response over a large domain of technical documents is disclosed. First, the grammar and morphology of the statements and instructions expressed in the technical documents is used to filter training data to extract the text that is most information-rich, that is the text that contains domain-specific jargon, in context. This training data is then vectorized and fed as input to an SBERT neural network model that learns an embedding of related words and terms in the text, i.e. the relationship between a given set of words contained in a user's query and the instructions from the technical documentation text most likely to assist in the user's operations. There are two parsing tasks. The first is to select a minimal sample of sentences from the document corpus that capture the domain-specific terminology (jargon). The result is set of sentences used to train BERT and SBERT. The second parsing task to create a set of action-trigger phrases from the document corpus. The trigger potentially matches a user query and the action is the related task.
-
公开(公告)号：US20220300404A1
公开(公告)日：2022-09-22
申请号：US17202445
申请日：2021-03-16
Applicant: Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Inventor： Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L. Bruso
Abstract: A method for creating a learning model that evaluates risks of applying commits in a third-party product to a dependent product is disclosed. The method includes collecting data on past commits; training the learning model using the collected data; and using the learning model to determine if future commits are problematic.
-
公开(公告)号：US20220121814A1
公开(公告)日：2022-04-21
申请号：US17478948
申请日：2021-09-19
Applicant: Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
Inventor： Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
IPC: G06F40/205 , G06F16/93 , G06F16/245
Abstract: A method of parsing implicit tables within a document includes parsing, by a processor, a document to determine a pattern for a set of text that sets apart the information contained therein from the rest of the text; determining, by the processor, from the pattern of spacing, a first descriptive phrase and a second descriptive phrase; and assigning, by the processor, the first descriptive phrase as an action and the second descriptive phrase as a trigger.
-
公开(公告)号：US20220121666A1
公开(公告)日：2022-04-21
申请号：US17478947
申请日：2021-09-19
Applicant: Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
Inventor： Mark Rosno , Patrick Deziel , Christopher Korzenowski , Rebecca Bilbro , Kelsey L. Bruso , Robert Malek
IPC: G06F16/2453 , G06F16/2457 , G06F16/93 , G06N3/08 , G06F40/40
Abstract: A method of creating a trained database from a document corpus includes creating a tailored neural network for the document corpus by using sentences to create word-level association and sentence-level association; and applying action-trigger phrase sets, created front the document corpus independent of creating the tailored neural network, to the tailored neural network to create a trained database; wherein processing a query through the trained database, rather than the document corpus, increases the speed of processing the query and increases the accuracy of the result.
-
公开(公告)号：US20220300275A1
公开(公告)日：2022-09-22
申请号：US17202441
申请日：2021-03-16
Applicant: Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L Bruso
Inventor： Patrick Deziel , James M. Plasek , Rami Reddy Nelluru , Kelsey L Bruso
Abstract: A method for creating a learning model that evaluates risks of applying commits in a third-party product to a dependent product is disclosed. The method includes collecting data on past commits; training the learning model using the collected data; and using the learning model to determine if future commits are problematic.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.017 seconds)
